Hugging Face's logo

vania2911
/
11_6kmslsamples

Transformers
TensorBoard
Safetensors
marian
text2text-generation
Generated from Trainer
Model card Files
xet
 Metrics Community
vania2911 commited on
Commit
1d2c5a3
·
verified ·
1 Parent(s): 4550de6

End of training

Browse files
Files changed (4) hide show
  1. README.md +38 -39
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Mar08_14-46-35_631e7f0133ea/events.out.tfevents.1741445232.631e7f0133ea.1393.0 +2 -2
README.md CHANGED
@@ -16,12 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4832
20
- - Model Preparation Time: 0.0033
21
- - Bleu Msl: 76.2719
22
- - Bleu Asl: 0
23
- - Ter Msl: 12.4158
24
- - Ter Asl: 100
25
 
26
  ## Model description
27
 
@@ -51,43 +50,43 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Bleu Msl | Bleu Asl | Ter Msl | Ter Asl |
55
- |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:--------:|:--------:|:-------:|:-------:|
56
- | No log | 1.0 | 292 | 0.2395 | 0.0033 | 11.4499 | 88.9288 | 91.0976 | 5.6389 |
57
- | 0.4467 | 2.0 | 584 | 0.1630 | 0.0033 | 72.4836 | 90.3437 | 18.1588 | 5.1480 |
58
- | 0.4467 | 3.0 | 876 | 0.1537 | 0.0033 | 69.4982 | 89.2613 | 22.9135 | 5.8073 |
59
- | 0.0901 | 4.0 | 1168 | 0.1488 | 0.0033 | 67.2310 | 75.4270 | 22.6606 | 13.0313 |
60
- | 0.0901 | 5.0 | 1460 | 0.1438 | 0.0033 | 72.7268 | 91.0640 | 18.4117 | 4.4887 |
61
- | 0.0479 | 6.0 | 1752 | 0.1443 | 0.0033 | 74.3024 | 84.6282 | 16.6920 | 5.5828 |
62
- | 0.0306 | 7.0 | 2044 | 0.1468 | 0.0033 | 75.8427 | 88.1935 | 15.3768 | 6.1860 |
63
- | 0.0306 | 8.0 | 2336 | 0.1523 | 0.0033 | 72.8626 | 90.7097 | 18.8670 | 5.0077 |
64
- | 0.022 | 9.0 | 2628 | 0.1419 | 0.0033 | 71.9710 | 89.9411 | 15.8827 | 5.4566 |
65
- | 0.022 | 10.0 | 2920 | 0.1481 | 0.0033 | 72.5502 | 91.3971 | 18.7152 | 4.4747 |
66
- | 0.0217 | 11.0 | 3212 | 0.1414 | 0.0033 | 71.0317 | 91.3192 | 19.5751 | 4.8815 |
67
- | 0.0156 | 12.0 | 3504 | 0.1435 | 0.0033 | 76.9787 | 83.9106 | 14.3652 | 11.2498 |
68
- | 0.0156 | 13.0 | 3796 | 0.1513 | 0.0033 | 75.6635 | 83.1054 | 15.7815 | 11.8390 |
69
- | 0.01 | 14.0 | 4088 | 0.1491 | 0.0033 | 74.8931 | 91.4009 | 16.5402 | 5.0077 |
70
- | 0.01 | 15.0 | 4380 | 0.1502 | 0.0033 | 75.7380 | 90.2261 | 17.0460 | 5.7091 |
71
- | 0.0088 | 16.0 | 4672 | 0.1474 | 0.0033 | 76.2381 | 92.3039 | 16.4896 | 4.1661 |
72
- | 0.0088 | 17.0 | 4964 | 0.1493 | 0.0033 | 77.6706 | 92.2754 | 15.3768 | 4.4045 |
73
- | 0.0076 | 18.0 | 5256 | 0.1519 | 0.0033 | 73.3253 | 89.7627 | 17.9565 | 5.9195 |
74
- | 0.0057 | 19.0 | 5548 | 0.1473 | 0.0033 | 72.4356 | 91.0144 | 19.2210 | 4.7833 |
75
- | 0.0057 | 20.0 | 5840 | 0.1520 | 0.0033 | 75.0746 | 90.0677 | 17.0460 | 5.8493 |
76
- | 0.005 | 21.0 | 6132 | 0.1509 | 0.0033 | 75.7113 | 82.0543 | 16.1861 | 13.2277 |
77
- | 0.005 | 22.0 | 6424 | 0.1487 | 0.0033 | 76.6081 | 82.3037 | 15.4780 | 12.5684 |
78
- | 0.0041 | 23.0 | 6716 | 0.1500 | 0.0033 | 76.6765 | 81.3603 | 16.1356 | 13.7186 |
79
- | 0.004 | 24.0 | 7008 | 0.1497 | 0.0033 | 78.6303 | 82.3583 | 14.6181 | 12.8349 |
80
- | 0.004 | 25.0 | 7300 | 0.1509 | 0.0033 | 77.9463 | 82.7968 | 15.1745 | 12.1896 |
81
- | 0.0028 | 26.0 | 7592 | 0.1500 | 0.0033 | 77.0621 | 82.5839 | 15.3263 | 12.6806 |
82
- | 0.0028 | 27.0 | 7884 | 0.1517 | 0.0033 | 76.1682 | 82.2440 | 16.1356 | 13.1716 |
83
- | 0.0025 | 28.0 | 8176 | 0.1518 | 0.0033 | 75.5286 | 82.0875 | 16.0344 | 13.3118 |
84
- | 0.0025 | 29.0 | 8468 | 0.1518 | 0.0033 | 76.4287 | 82.3060 | 15.4780 | 13.0874 |
85
- | 0.0022 | 30.0 | 8760 | 0.1519 | 0.0033 | 76.3073 | 82.3498 | 15.5286 | 13.0453 |
86
 
87
 
88
  ### Framework versions
89
 
90
- - Transformers 4.49.0
91
  - Pytorch 2.5.1+cu124
92
  - Datasets 3.3.2
93
  - Tokenizers 0.21.0
 
16
 
17
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0714
20
+ - Bleu Msl: 82.3301
21
+ - Bleu Asl: 97.1735
22
+ - Ter Msl: 11.2456
23
+ - Ter Asl: 1.4638
 
24
 
25
  ## Model description
26
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Bleu Msl | Bleu Asl | Ter Msl | Ter Asl |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------:|:-------:|
55
+ | 0.3888 | 1.0 | 567 | 0.1194 | 52.4711 | 92.5612 | 26.0716 | 3.7483 |
56
+ | 0.1178 | 2.0 | 1134 | 0.0928 | 12.3994 | 94.4382 | 95.6631 | 2.8878 |
57
+ | 0.0785 | 3.0 | 1701 | 0.0791 | 27.7561 | 95.2400 | 14.7756 | 2.4407 |
58
+ | 0.0607 | 4.0 | 2268 | 0.0784 | 76.2031 | 95.4984 | 12.9602 | 2.2967 |
59
+ | 0.048 | 5.0 | 2835 | 0.0745 | 69.5670 | 95.6702 | 18.6586 | 2.2539 |
60
+ | 0.0392 | 6.0 | 3402 | 0.0718 | 78.5639 | 96.0612 | 12.9097 | 1.9966 |
61
+ | 0.0324 | 7.0 | 3969 | 0.0697 | 80.1654 | 96.0441 | 11.2960 | 2.0548 |
62
+ | 0.0217 | 8.0 | 4536 | 0.0714 | 78.6078 | 96.3918 | 13.1114 | 1.9568 |
63
+ | 0.0177 | 9.0 | 5103 | 0.0732 | 80.7119 | 96.0813 | 11.8507 | 2.0916 |
64
+ | 0.0178 | 10.0 | 5670 | 0.0717 | 79.8444 | 96.2730 | 11.9516 | 1.9783 |
65
+ | 0.0142 | 11.0 | 6237 | 0.0692 | 68.7637 | 96.4883 | 20.9279 | 1.8251 |
66
+ | 0.0144 | 12.0 | 6804 | 0.0700 | 80.5359 | 94.8578 | 12.2542 | 3.4420 |
67
+ | 0.0119 | 13.0 | 7371 | 0.0718 | 80.6068 | 96.3883 | 11.7499 | 1.8650 |
68
+ | 0.0099 | 14.0 | 7938 | 0.0710 | 79.7237 | 96.5317 | 12.3046 | 1.7915 |
69
+ | 0.0089 | 15.0 | 8505 | 0.0725 | 79.6613 | 96.4755 | 11.9012 | 1.8986 |
70
+ | 0.008 | 16.0 | 9072 | 0.0720 | 82.1357 | 96.8505 | 10.9430 | 1.6169 |
71
+ | 0.0062 | 17.0 | 9639 | 0.0702 | 83.0745 | 96.7340 | 10.6909 | 1.6904 |
72
+ | 0.0059 | 18.0 | 10206 | 0.0698 | 79.5220 | 96.8042 | 11.8507 | 1.6628 |
73
+ | 0.0072 | 19.0 | 10773 | 0.0713 | 80.4408 | 96.8836 | 11.4473 | 1.6322 |
74
+ | 0.0049 | 20.0 | 11340 | 0.0716 | 81.6404 | 96.8682 | 11.2456 | 1.6292 |
75
+ | 0.0044 | 21.0 | 11907 | 0.0713 | 81.7670 | 96.9006 | 11.1952 | 1.6873 |
76
+ | 0.0035 | 22.0 | 12474 | 0.0718 | 80.5118 | 96.9222 | 11.4977 | 1.6230 |
77
+ | 0.0031 | 23.0 | 13041 | 0.0720 | 81.2657 | 97.0022 | 11.0439 | 1.5924 |
78
+ | 0.0031 | 24.0 | 13608 | 0.0723 | 82.0082 | 96.9102 | 11.0439 | 1.5955 |
79
+ | 0.0022 | 25.0 | 14175 | 0.0721 | 82.1310 | 97.0355 | 10.7917 | 1.5403 |
80
+ | 0.0022 | 26.0 | 14742 | 0.0726 | 83.0873 | 97.0320 | 10.8926 | 1.5373 |
81
+ | 0.002 | 27.0 | 15309 | 0.0711 | 82.5284 | 97.0864 | 10.9430 | 1.4944 |
82
+ | 0.002 | 28.0 | 15876 | 0.0710 | 83.1909 | 97.1182 | 10.6909 | 1.4852 |
83
+ | 0.0015 | 29.0 | 16443 | 0.0713 | 82.5500 | 97.0790 | 11.0943 | 1.5005 |
84
+ | 0.0013 | 30.0 | 17010 | 0.0714 | 82.3301 | 97.1735 | 11.2456 | 1.4638 |
85
 
86
 
87
  ### Framework versions
88
 
89
+ - Transformers 4.48.3
90
  - Pytorch 2.5.1+cu124
91
  - Datasets 3.3.2
92
  - Tokenizers 0.21.0
generation_config.json CHANGED
@@ -12,5 +12,5 @@
12
  "num_beams": 4,
13
  "pad_token_id": 33252,
14
  "renormalize_logits": true,
15
- "transformers_version": "4.49.0"
16
  }
 
12
  "num_beams": 4,
13
  "pad_token_id": 33252,
14
  "renormalize_logits": true,
15
+ "transformers_version": "4.48.3"
16
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f492035a6554a04286a88cf64546785344e836b2adb0235548844e78c28769
3
  size 244826404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e071b0dcb5fc1e823a83501cb968b67677c13cadda04969c10c74d8e9c70ddea
3
  size 244826404
runs/Mar08_14-46-35_631e7f0133ea/events.out.tfevents.1741445232.631e7f0133ea.1393.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2346e7abcf54a609df46608b04c43cab42b92f5942c2f810db425543ccbbacfb
3
- size 27093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88aef044a4012601751a4ffc7e0db5fa90da7ef9f2033f40e6863318a2ea5c31
3
+ size 27939